Table 5 The hyperparameters used to train the PE segmentation model
From: Automatic deep learning-based pleural effusion segmentation in lung ultrasound images
Batch size | 32 |
Batch normalization | True |
Dropout | 0.5 |
Epochs | 50 |
Learning rate (Adam) | \(10^{-5}\) |
Loss function | Binary Cross Entropy |